# Large Language Model Unlearning

arXiv: https://arxiv.org/abs/2310.10683 · HTML: https://mlsanity.com/paper/2310.10683/

## Key facts

- Cited by 302 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 37 of its 56 references that are in the map.
- First posted on arXiv 14 Oct 2023.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 37)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023)
- [HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2305.11747/) (2023)
- [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://mlsanity.com/paper/2007.02923/) (2020)
- [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [Quark: Controllable Text Generation with Reinforced Unlearning](https://mlsanity.com/paper/2205.13636/) (2022)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [Secrets of RLHF in Large Language Models Part I: PPO](https://mlsanity.com/paper/2307.04964/) (2023)
- [In-Context Unlearning: Language Models as Few Shot Unlearners](https://mlsanity.com/paper/2310.07579/) (2023)

## Built on by (most cited first, 30 of 302)

- [The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning](https://mlsanity.com/paper/2403.03218/) (2024)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [MUSE: Machine Unlearning Six-Way Evaluation for Language Models](https://mlsanity.com/paper/2407.06460/) (2024)
- [Rethinking Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2402.08787/) (2024)
- [Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities](https://mlsanity.com/paper/2408.07666/) (2024)
- [Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs](https://mlsanity.com/paper/2407.15549/) (2024)
- [Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning](https://mlsanity.com/paper/2410.07163/) (2024)
- [Tamper-Resistant Safeguards for Open-Weight LLMs](https://mlsanity.com/paper/2408.00761/) (2024)
- [An Adversarial Perspective on Machine Unlearning for AI Safety](https://mlsanity.com/paper/2409.18025/) (2024)
- [Large Language Model Unlearning via Embedding-Corrupted Prompts](https://mlsanity.com/paper/2406.07933/) (2024)
- [Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference](https://mlsanity.com/paper/2406.08607/) (2024)
- [Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning](https://mlsanity.com/paper/2406.13356/) (2024)
- [Catastrophic Failure of LLM Unlearning via Quantization](https://mlsanity.com/paper/2410.16454/) (2024)
- [Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond](https://mlsanity.com/paper/2502.05374/) (2025)
- [RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models](https://mlsanity.com/paper/2406.10890/) (2024)
- [LLM Unlearning via Loss Adjustment with Only Forget Data](https://mlsanity.com/paper/2410.11143/) (2024)
- [Uncovering Safety Risks of Large Language Models through Concept Activation Vector](https://mlsanity.com/paper/2404.12038/) (2024)
- [Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond](https://mlsanity.com/paper/2502.19301/) (2025)
- [Large Language Model Safety: A Holistic Survey](https://mlsanity.com/paper/2412.17686/) (2024)
- [A Closer Look at Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2410.08109/) (2024)
- [On Large Language Model Continual Unlearning](https://mlsanity.com/paper/2407.10223/) (2024)
- [Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge](https://mlsanity.com/paper/2404.05880/) (2024)
- [Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs](https://mlsanity.com/paper/2406.09324/) (2024)
- [UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI](https://mlsanity.com/paper/2407.00106/) (2024)
- [Direct Unlearning Optimization for Robust and Safe Text-to-Image Models](https://mlsanity.com/paper/2407.21035/) (2024)
- [JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework](https://mlsanity.com/paper/2410.12855/) (2024)
- [Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models](https://mlsanity.com/paper/2405.12523/) (2024)
- [Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning](https://mlsanity.com/paper/2403.07362/) (2024)
- [LLM Unlearning via Neural Activation Redirection](https://mlsanity.com/paper/2502.07218/) (2025)
- [Digital Forgetting in Large Language Models: A Survey of Unlearning Methods](https://mlsanity.com/paper/2404.02062/) (2024)

## Abstract (arXiv)

We study how to perform unlearning, i.e. forgetting undesirable misbehaviors, on large language models (LLMs). We show at least three scenarios of aligning LLMs with human preferences can benefit from unlearning: (1) removing harmful responses, (2) erasing copyright-protected content as requested, and (3) reducing hallucinations. Unlearning, as an alignment technique, has three advantages. (1) It only requires negative (e.g. harmful) examples, which are much easier and cheaper to collect (e.g. via red teaming or user reporting) than positive (e.g. helpful and often human-written) examples required in RLHF (RL from human feedback). (2) It is computationally efficient. (3) It is especially effective when we know which training samples cause the misbehavior. To the best of our knowledge, our work is among the first to explore LLM unlearning. We are also among the first to formulate the settings, goals, and evaluations in LLM unlearning. We show that if practitioners only have limited resources, and therefore the priority is to stop generating undesirable outputs rather than to try to generate desirable outputs, unlearning is particularly appealing. Despite only having negative samples, our ablation study shows that unlearning can still achieve better alignment performance than RLHF with just 2% of its computational time.